import pandas as pd
from sklearn import preprocessing
x = df.values #returns a numpy array
min_max_scaler = preprocessing.MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(x)
df = pd.DataFrame(x_scaled)# min-max normalization:
df=(df-df.min())/(df.max()-df.min())
# or...
# mean normalization:
df=(df-df.mean())/df.std()>>> from sklearn import preprocessing
>>>
>>> data = [100, 10, 2, 32, 31, 949]
>>>
>>> preprocessing.normalize([data])
array([[0.10467389, 0.01046739, 0.00209348, 0.03349564, 0.03244891,0.99335519]])
# define a method to scale data, looping thru the columns, and passing a scaler
def scale_data(data, columns, scaler):
for col in columns:
data[col] = scaler.fit_transform(data[col].values.reshape(-1, 1))
return data